activity
20242026
most citedCompositional Shielding and Reinforcement Learning for Multi-Agent Systems

3 citations · 7 across the 6 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2026

Adaptive Probabilistic Shielding by Learning MDPs for Safe Reinforcement Learning

Astrid Horn Brorholt, Maris F. L. Galesloot, Nils Jansen +2

Probabilistic shielding is a technique for safe reinforcement learning (RL). Typically, a static observer -- called the shield -- constrains the learning agent's actions to those f…